Memory-Efficient Finetuning

Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning featured image
Deep Learning

Dr<sup>2</sup>Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning

Large pretrained models are increasingly crucial in modern computer vision tasks. These models are typically used in downstream tasks by end-to-end finetuning, which is highly …

avatar
Chen Zhao
•
Read more
End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames featured image
Deep Learning

End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames

Recently, temporal action detection (TAD) has seen significant performance improvement with end-to-end training. However, due to the memory bottleneck, only models with limited …

Shuming liu
•
Read more